Professional Documents
Culture Documents
A Small Intro of AI
A Small Intro of AI
Don.S Ph.D
Don.S
Course Objectives
Don.S
Don.S
Don.S
Syllabus
Don.S
Don.S
Don.S
Textbooks
Don.S
Don.S
Don.S
Course Evaluation
Don.S
Don.S
Sci-Fi
Don.S
AI?
Don.S
Don.S
Don.S
Today
Don.S
• What is artificial intelligence?
Don.S
Don.S
Nature of learning
Don.S
Don.S
Don.S
Don.S
Don.S
Don.S
AI definitions
Don.S
Don.S
Don.S Cognitive Science – Understanding Intelligence
Don.S
Don.S
Don.S
Don.S
• It was John McCarthy after his PhD in 1951, he moved from Stanford
to Dartmouth college, the official birth place of AI
• He organized a two month workhop, and an attempt was made to
find out how to make machines use language, from abstraction and
concepts, solve kinds of problems now reserved for humans and
improve themselves.
• There were 10 persons, in that workshop and no lead to
breakthroughs, but it did introduce all the major figures each other.
• Next 20 years , AI will dominate by these people and their students at
MIT, CMU, Stanford and IBM.
Don.S
Don.S
Previous class Graphical representation of Goal state
Don.S
Don.S
Artificial Intelligence: The Original idea
Don.S
Don.S
Don.S
Don.S
Classical AI : Successes
Don.S
• Search engines
• Formal games(Chess!)
• Text processing systems
• Data mining systems
• Appliances Deep blue project
• Control systems
Don.S
Don.S
Classical AI: Failures
Don.S
Don.S
Don.S
What is intelligence?
Don.S
Don.S
– H: Men are all alike
Don.S
– E: In what way?
– H: They’re always bugging us about something or Don.S
another.
– E: Can you be more specific?
– H: Well, my boyfriend made me come here.
Example
– E: Your boyfriend made you come here? Eliza Dialog
– H: He says I’m depressed much of the time.
– E: I am sorry to hear you are depressed.
– H: It’s true. I am unhappy.
– E: Do you think coming here will help you not to be
unhappy?
– H: I need some help, that much seems certain.
– E: What would it mean to you if you got some help?
– H: Perhaps I could learn to get along with my mother.
– E: Tell me more about your family
Don.S
(?* ?x) hello (?* ?y)
Don.S (How do you do. Please state your problem.)
(?* ?x) I want (?* ?y)
(What would it mean if you got ?y) Don.S
(Why do you want ?y)
(Suppose you got ?y soon)
(?* ?x) if (?* ?y) Eliza
(Do you really think its likely that ?y)
(Do you wish that ?y)
Rules
(What do you think about ?y) (Really-- if ?y)
(?* ?x) no (?* ?y) (Why not?)
(You are being a bit negative) Eliza also has a
(Are you saying "NO" just to be negative?) rule to swap
(?* ?x) I was (?* ?y) (Were you really?) ‘I’ and ‘my’
(Perhaps I already knew you were ?y) to ‘you’ and ‘your’
(Why do you tell me you were ?y now?)
(?* ?x) I feel (?* ?y) (Do you often feel ?y ?)
(?* ?x) I felt (?* ?y)
(What other feelings do you have?) Don.S
Don.S
ALICE Demo
Jerry: my name is jerry.
Don.S
ALICE: Hey jerry.
Jerry: do you know Turing?
ALICE: A brilliant and tragic figure in the history of computer science.
Jerry: who else do you know?
ALICE: Hugh Loebner, Robby Garner, and Steven Spielberg
Jerry: which film do you like?
ALICE: My favorite movie is Teknolust. Have you seen it?
Jerry: no.
ALICE: I would recommend you check it out.
Jerry: what is it about?
ALICE: Science fiction.
Jerry: do you remember my name?
ALICE: Your name is jerry, seeker.
• With Eliza or Alice like rules, we can eventually solve the Turing Test –
it just takes writing enough rules
• Does the system understand what it is responding to?
• No, neither Eliza nor Alice understand the text, its just that Alice has better,
more in depth and wider ranging rules
• We could build a representation that models some real-world domain
and knowledge base
Don.S
Don.S
Cyc Project
Don.S
Don.S
Don.S
About Cyc
Don.S
“People have silly reason why computers don’t really think. The answer
is we haven’t programmed them right: they don’t have much common
sense. There’s been only one large project to do something about that,
that’s famous Cyc Project “
Don.S
Don.S
Cyc Project
Don.S
• Current Status
• Cyc’s KB includes more than 10,000 predicates, millions of collections and
concepts, and more than 25 million assertions.
Don.S
Don.S
Don.S
Don.S
Don.S
The Chinese Room Problem
• From John Searle, Philosopher, in an attempt to
Don.S
demonstrate that computers cannot be intelligent
– The room consists of you, a book, a storage area (optional),
and a mechanism for moving information to and from the
room to the outside
• a Chinese speaking individual provides a question for you in writing
• you are able to find a matching set of symbols in the book (and
storage) and write a response, also in Chinese
www.vit.ac.in Don.S
Storage You Book of Chinese Symbols
Don.S
Chinese Room:
An Analogy for a Computer
Don.S
Note: Searle’s original Chinese Room actually was based on a
Script that was implemented in Chinese, our version is just a
variation on the same theme
User Input I/O pathway (bus) Output
Don.S
A Brief History of AI: 1950s
Don.S
• Computers were thought of as an electronic brains
• Term “Artificial Intelligence” coined by John McCarthy Don.S
Don.S
Today: The New (Old) AI
Don.S • Look around, who is doing AI research?
• By their own admission, AI researchers are not doing “AI”, they are
doing Don.S
• Intelligent agents, multi-agent systems/collaboration
• Ontologies
• Machine learning and data mining
• Adaptive and perceptual systems
• Robotics, path planning
• Search engines, filtering, recommendation systems
• Areas of current research interest:
• NLU/Information Retrieval, Speech Recognition
• Planning/Design, Diagnosis/Interpretation
• Sensor Interpretation, Perception, Visual Understanding
• Robotics
• Approaches
• Knowledge-based
• Ontologies
• Probabilistic (HMM, Bayesian Nets)
• Neural Networks, Fuzzy Logic, Genetic Algorithms
Don.S
Don.S
Don.S
Don.S